Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hold and stop actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Creativity
    0.44
    ట్స్
    0.43
     Veget
    0.43
    ვნ
    0.42
     comporte
    0.42
     Tourists
    0.42
    俎
    0.42
    팡
    0.41
     defy
    0.41
    മ്പ
    0.40
    POSITIVE LOGITS
    source
    0.44
    Ra
    0.44
    Source
    0.41
    production
    0.40
    per
    0.40
    ku
    0.39
    decision
    0.39
    Ku
    0.39
    collection
    0.38
    km
    0.38
    Act Density 0.000%

    No Known Activations